Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    examples for comparison or illustration

    oai_token-act-pair · gpt-3.5-turbo

    references to examples or cases in a discussion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ormal
    -0.80
    ogun
    -0.72
    ves
    -0.71
    ements
    -0.69
    sil
    -0.69
    inal
    -0.69
     Flavoring
    -0.69
    orously
    -0.69
    ELY
    -0.69
     bang
    -0.67
    POSITIVE LOGITS
    ©¶æ¥µ
    0.79
     owing
    0.76
    DonaldTrump
    0.72
    herty
    0.69
     Schn
    0.67
     "@
    0.66
     Katz
    0.63
     Skydragon
    0.63
     subp
    0.63
    ,...
    0.63
    Act Density 0.027%

    No Known Activations